@andreprado/agentkit 0.1.0-alpha.3 → 0.1.0-alpha.5

package/src/templates/blank.ts

@@ -65,6 +65,7 @@ node_modules/
         contents: `# Optional: only needed after switching agentkit.config.ts to a Pi-backed real provider.
 OPENAI_API_KEY=
 ANTHROPIC_API_KEY=
+OPENROUTER_API_KEY=
 `,
       },
       {
@@ -151,6 +152,7 @@ Start building immediately:
 - Edit \`prompts/instructions.md\` for the agent behavior.
 - Edit \`agentkit.config.ts\` for provider, tools, secrets, access, and storage.
 - Add TypeScript tools under \`tools/\` when the requested agent needs actions or external data.
+- Do not wait for a wizard or recipe. AgentKit provides the scaffold and contract; you decide the implementation from the owner's brief.
 - Ask follow-up questions only when missing information blocks a safe local implementation.
 - State assumptions in the final response.
 
@@ -170,6 +172,13 @@ Start building immediately:
 - \`npm run agentkit -- env list\`: list local secret names without printing values.
 - \`npm run agentkit -- docs full\`: print the full AgentKit contract path.
 
+## Testing With A UI
+
+- Local UI: run \`npm run dev\`, open the printed \`Chat:\` URL, and tell the owner the exact URL.
+- Hosted UI: after \`npm run agentkit -- deploy\`, run \`npm run agentkit -- chat-ui --deploy\`, open the printed \`Chat:\` URL, and tell the owner it is connected to the hosted deploy.
+- \`test/fake\` is deterministic. It is useful for scaffold checks, direct tool checks, and fake-provider evals, but it does not validate natural conversation quality.
+- Before claiming real conversation behavior is tested, ask the owner which provider to use: OpenRouter, OpenAI, Anthropic, or another supported provider. Do not choose for them.
+
 This blank capsule starts with the built-in \`test/fake\` provider, so local chat works without secrets or internet access. It is also deploy-ready by default: the user can edit the prompt, add tools, and run \`npm run agentkit -- deploy\`.
 
 ## Local Runtime Contract
@@ -213,11 +222,13 @@ Use \`ctx.db\` as the canonical helper. \`ctx.database\` and \`ctx.storage.sql\`
 - Put production secret values into managed secrets with \`npm run agentkit -- secret set <NAME> --from-local-env\`, \`--from-env\`, or \`--stdin\`, not into committed files or shell history.
 - The user should not choose a deploy target, create hosted databases, create buckets, copy production secrets into this capsule, or run operator/admin commands.
 - Hosted deploy writes the local chat/UI deploy access token to \`.agentkit/chat-access-token.json\`. Create extra client-facing tokens with \`npm run agentkit -- access token create <name> --out <path>\`.
+- Use \`npm run agentkit -- deploy --smoke "hello"\` or \`npm run agentkit -- deploy smoke --message "hello"\` for an official hosted chat smoke check.
 
 ## Rules
 
 - Keep required local secret names in \`.env.schema\` and values in ignored \`.env\`. AgentKit local commands load \`.env\` directly.
 - Real providers are resolved by AgentKit through the internal Pi SDK backend; keep project code on \`@andreprado/agentkit\`.
+- The owner must choose the real provider before you switch from \`test/fake\`. Update \`agentkit.config.ts\`, \`.env.schema\`, and local/hosted secrets after that choice.
 - Do not commit \`.env\` or \`.agentkit/\`.
 - Edit the agent contract in \`agentkit.config.ts\`.
 - Edit instructions in \`prompts/instructions.md\`.
@@ -243,6 +254,7 @@ Turn the request into a working local capsule:
 - Update \`agentkit.config.ts\` when tools, secrets, provider, or access rules change.
 - Add TypeScript tools under \`tools/\` for real actions or external data.
 - Keep the first version runnable with \`test/fake\` unless the owner explicitly asks for a real provider.
+- Do not use a wizard or recipe. Build the capsule directly from the scaffold, the AgentKit contract, and the owner's brief.
 - Make practical assumptions and list them in your final response.
 - Ask follow-up questions only when missing information blocks a safe local implementation.
 
@@ -254,6 +266,8 @@ npm run agentkit -- inspect
 npm run chat -- --message "hello"
 \`\`\`
 
+\`test/fake\` proves the scaffold and deterministic tool paths. It does not prove natural conversation quality.
+
 \`agentkit new\` installs dependencies by default. Run \`npm install\` only if the capsule was created with \`--no-install\`, install failed, or \`node_modules\` was deleted.
 
 Set local development secrets without opening code:
@@ -264,6 +278,27 @@ npm run agentkit -- inspect
 npm run chat -- --message "hello"
 \`\`\`
 
+## Testing With A UI
+
+Local UI:
+
+\`\`\`sh
+npm run dev
+\`\`\`
+
+Open the printed \`Chat:\` URL and tell the owner the exact URL.
+
+Hosted deploy UI:
+
+\`\`\`sh
+npm run agentkit -- deploy
+npm run agentkit -- chat-ui --deploy
+\`\`\`
+
+Open the printed \`Chat:\` URL and tell the owner this local UI is connected to the hosted deploy.
+
+Before claiming real conversation behavior has been tested, ask the owner which provider to use: OpenRouter, OpenAI, Anthropic, or another supported provider. Do not choose for them. After they choose, update \`agentkit.config.ts\`, \`.env.schema\`, local secrets, hosted secrets if deploying, then rerun chat/UI checks.
+
 If you add a tool, also run a fake-provider tool smoke test:
 
 \`\`\`sh
@@ -287,6 +322,7 @@ This capsule is hosted-deploy ready by default.
 5. Put production secrets into managed secrets with \`npm run agentkit -- secret set <NAME> --from-local-env\`, \`--from-env\`, or \`--stdin\`.
 6. Run \`npm run agentkit -- deploy\`.
 7. Run \`npm run agentkit -- chat-ui --deploy\` to test the hosted agent through a local UI using the auto-created \`.agentkit/chat-access-token.json\`. Create extra client-facing deploy access tokens with \`npm run agentkit -- access token create <name> --out <path>\` when a separate website or app needs its own credential.
+8. Use \`npm run agentkit -- deploy --smoke "hello"\` during deploy or \`npm run agentkit -- deploy smoke --message "hello"\` afterward for an official hosted smoke check.
 
 AgentKit owns hosted infrastructure and production secrets. Do not put production secret values in this capsule. Do not run operator/admin commands from a user capsule.
 `,
@@ -303,6 +339,7 @@ Use AgentKit conventions when editing this project.
 - Local runtime state lives in \`.agentkit/\` and should not be committed.
 - The default provider is \`test/fake\`, which needs no secrets.
 - Real providers run through AgentKit's internal Pi SDK backend.
+- Ask the owner which real provider to use before switching from \`test/fake\`; do not choose OpenRouter, OpenAI, or Anthropic automatically.
 - Production secrets must be managed secrets, not committed files.
 - Keep required local secret names in \`.env.schema\` and values in ignored \`.env\`. AgentKit local commands load \`.env\` directly.
 - Treat the owner's natural-language request as the brief and start implementing inside this capsule.
@@ -328,6 +365,10 @@ When a real provider or tool needs a local development secret, keep the required
 
 \`npm run dev\` runs the whole capsule locally. It should expose local chat, API, inspect, and storage endpoints.
 
+For UI testing, run \`npm run dev\` and open the printed \`Chat:\` URL. After hosted deploy, run \`npm run agentkit -- chat-ui --deploy\` and open its printed \`Chat:\` URL.
+
+\`test/fake\` does not validate real conversation quality. The owner must choose OpenRouter, OpenAI, Anthropic, or another supported provider before real model behavior is tested.
+
 ## Files
 
 - \`agentkit.config.ts\`: agent contract.